gpt-oss-120b

Name: openai/gpt-oss-120b
Brand: OpenAI
Price: 0.1 USD
Availability: InStock

OpenAIAdded Jul 11, 2026

Model idopenai/gpt-oss-120b

OpenAI's open-weight model, 117B parameters with 5B active per token, under the Apache 2.0 licence. Designed for reasoning and agent tasks, with native function calling and structured outputs.

Cost /1M tokens

$0.10input

$0.10cached

$0.60output

Context

128Ktokens

Live speed

181 tok/s · 0.34s to first token

Speed

Throughput users got on gpt-oss-120b with Keln API in the last 24 hours.

Latency

Time to first token users got on gpt-oss-120b with Keln API in the last 24 hours.

Capabilities

Input

Text

Tool calling

Yes

JSON output

Yes

Reasoning

Yes

Web search

With opt-in

Data retention

Zero

Use the API

Create an API key, save it to KELN_API_KEY, then call the endpoint below.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.keln.ai/v1/",
    api_key=os.environ.get("KELN_API_KEY"),
)

resp = client.chat.completions.create(
    model="openai/gpt-oss-120b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)